{"id":"https://openalex.org/W2150314414","doi":"https://doi.org/10.1109/icassp.2008.4518668","title":"Exploiting prosodic and lexical features for tone modeling in a conditional random field framework","display_name":"Exploiting prosodic and lexical features for tone modeling in a conditional random field framework","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2150314414","doi":"https://doi.org/10.1109/icassp.2008.4518668","mag":"2150314414"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518668","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102519023","display_name":"Hongxiu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongxiu Wei","raw_affiliation_strings":["State Key Laboratory of Machine Perception, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772594","display_name":"Xinhao Wang","orcid":"https://orcid.org/0000-0002-0366-7543"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhao Wang","raw_affiliation_strings":["State Key Laboratory of Machine Perception, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448261","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-2853-5034"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["State Key Laboratory of Machine Perception, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004014436","display_name":"Dingsheng Luo","orcid":"https://orcid.org/0000-0001-6997-3984"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingsheng Luo","raw_affiliation_strings":["State Key Laboratory of Machine Perception, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["State Key Laboratory of Machine Perception, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102519023"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.7077,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.67923729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"4549","last_page":"4552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.8501483201980591},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7831709384918213},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7810977101325989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7193319797515869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103983759880066},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6427634358406067},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6115149259567261},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5672088861465454},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5151761770248413},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.48196694254875183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4748539924621582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45138296484947205},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10299476981163025},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10182473063468933}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8501483201980591},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7831709384918213},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7810977101325989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7193319797515869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103983759880066},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6427634358406067},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6115149259567261},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5672088861465454},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5151761770248413},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.48196694254875183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4748539924621582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45138296484947205},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10299476981163025},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10182473063468933},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518668","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W9334768","https://openalex.org/W50577135","https://openalex.org/W103244930","https://openalex.org/W155708904","https://openalex.org/W326551381","https://openalex.org/W1648698152","https://openalex.org/W1766290689","https://openalex.org/W1786981598","https://openalex.org/W2017591713","https://openalex.org/W2048804461","https://openalex.org/W2101694857","https://openalex.org/W2126289105","https://openalex.org/W2146423738","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W6604228424","https://openalex.org/W6606278960","https://openalex.org/W6637086781","https://openalex.org/W6637989529","https://openalex.org/W6638172229","https://openalex.org/W6682082992"],"related_works":["https://openalex.org/W2163278254","https://openalex.org/W1574213390","https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W2068412075","https://openalex.org/W156219719","https://openalex.org/W27484908","https://openalex.org/W2163874654","https://openalex.org/W2162582511","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Tonal":[0],"cues":[1,107],"play":[2],"an":[3,17],"important":[4],"role":[5],"in":[6,10],"distinguishing":[7],"ambiguous":[8],"words":[9],"Mandarin":[11,124],"speech":[12,99,125],"recognition.":[13],"This":[14],"paper":[15],"explores":[16],"innovative":[18],"tone":[19,70,90],"modeling":[20],"framework":[21],"using":[22],"prosodic":[23],"and":[24,53,96,112,130],"lexical":[25],"features,":[26],"as":[27,29],"well":[28],"syllable":[30],"context":[31],"information.":[32],"A":[33],"discriminative":[34],"model,":[35],"namely":[36],"a":[37,64],"Conditional":[38],"Random":[39],"Field":[40],"(CRF),":[41],"is":[42,45],"adopted,":[43],"which":[44,83],"sufficiently":[46],"flexible":[47],"to":[48,74,79,109],"handle":[49],"multiple":[50],"interacting":[51],"features":[52],"long-range":[54],"dependencies":[55],"of":[56,63,88,116],"observations.":[57],"After":[58],"the":[59,67,80,86,89,97,105],"first":[60],"pass":[61],"search":[62],"recognition":[65,126],"system,":[66],"CRF":[68],"based":[69],"models":[71],"are":[72],"employed":[73],"rerank":[75],"N-best":[76],"hypotheses":[77],"according":[78],"tonal":[81,106],"scores":[82],"can":[84],"represent":[85],"correctness":[87],"sequence":[91],"given":[92],"each":[93],"candidate":[94],"hypothesis":[95],"observed":[98],"signal.":[100],"Experiments":[101],"results":[102],"show":[103],"that":[104],"help":[108],"achieve":[110],"7.8%":[111],"8.6%":[113],"relative":[114],"reductions":[115],"character":[117],"error":[118],"rate":[119],"on":[120],"two":[121],"widely":[122],"used":[123],"tasks,":[127],"Hub-4":[128],"test":[129],"863":[131],"test.":[132]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}